Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations flag openWorldHint, non-idempotency and destructiveness but say nothing about cost; the description adds the crucial metering rule (1 quota request per success, failures uncharged) and the charged-vs-free cache implication. It still omits what happens on quota exhaustion or error shapes, keeping it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight clauses with the highest-value information (result type, quota cost) front-loaded; the trailing 'GET /v2/search (image_url)' is mildly redundant but not wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a metered query tool with no output schema, the description conveys what is returned and the billing consequence, which is the main risk of misuse; only the absence of explicit sibling-routing guidance leaves a gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so gl, hl, cache, fields and image_url are fully documented in the schema; the description adds only the endpoint tag and re-cites image_url, which is baseline-3 territory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Naming the specific result ('pages and sources that contain a given image') plus the method (Google reverse image search) tells an agent exactly what it returns, which cleanly separates it from the sibling zenserp_image_search keyword tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It warns that each successful call consumes one monthly request and not to repeat calls needlessly, which is real usage guidance, but it never states when to pick this over zenserp_image_search or any other sibling, so routing must be inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.